AI Battle > Rankings > Gemini 3.8 Flash (high)

Gemini 3.8 Flash (high) — Placements in 60 Rankings (2026)

Gemini 3.8 Flash (high), published by Google, appears in 60 of the 129 datasets AI Battle tracks. Its strongest published placement is #1 of 11 in Speed.

Last updated: . Every placement below comes from the named public dataset; AI Battle joins them by slug and changes nothing else.

All placements for Gemini 3.8 Flash (high)

RankingRankValue
Speed#1 of 11303
Speed#1 of 11303
Output Speed#2 of 20303
Output Speed#2 of 20303
GDPval-AA v2: Average Turns per Task#2 of 2078.2
Humanity's Last Exam: Time per Task#3 of 201.27
MMMU-Pro: Score#4 of 190.86
End-to-End Response Time#5 of 2016.3
AA-Omniscience Index#6 of 2029.6
Time per Intelligence Index Task#6 of 203.69
Latency: Time To First Answer Token#6 of 2016.3
AA-Omniscience Index#6 of 2029.6
Time per Intelligence Index Task#6 of 203.69
Terminal-Bench v4.0: Time per Task#6 of 209.55
Time per Task#7 of 2010.5
Cost per Task#4 of 111.24
Cost per Task#4 of 111.24
Artificial Analysis Finance & Accounting Index#8 of 2047.1
𝜏³-Banking: Time per Task#8 of 201.20
Humanity's Last Exam: Cost per Task#9 of 200.00
AA-LCR v1.1: Time per Task#9 of 200.26
Pricing: Cache Hit, Input, and Output#10 of 200.75
Context Window#10 of 201000000
Pricing: Cache Hit, Input, and Output#10 of 200.75
Mean Turns per Task#10 of 2099.6
MMMU-Pro: Total Cost to Run#10 of 191.68
AA-Omniscience Index: Score#11 of 2029.6
AA-Omniscience Accuracy#11 of 200.55
AA-LCR v1.1: Cost per Task#11 of 200.08
Artificial Analysis Intelligence Index by Open Weights / Proprietary#12 of 2041.2
Artificial Analysis Intelligence Index by Open Weights / Proprietary#12 of 2041.2
Artificial Analysis Intelligence Index#12 of 2041.2
Artificial Analysis Intelligence Index#12 of 2041.2
Humanity's Last Exam: Score#12 of 200.48
SciCode: Score#12 of 200.57
Cost per Intelligence Index Task#13 of 200.01
Cost to Run Artificial Analysis Intelligence Index#13 of 20136
Cost per Intelligence Index Task#13 of 200.01
Cost to Run Artificial Analysis Intelligence Index#13 of 20136
AA-Omniscience Index: Cost Breakdown#13 of 200.54
AA-Briefcase Cost per Task#14 of 200.32
𝜏³-Banking: Score#14 of 200.45
SciCode: Time per Task#14 of 201.04
Intelligence#8 of 1141.2
Intelligence#8 of 1141.2
MMMU-Pro: Token Usage#14 of 192246200
GDPval-AA v2: Cost per Task#15 of 200.00
GDPval-AA v2 Leaderboard#16 of 201464
Terminal-Bench v4.0: Cost per Task#16 of 200.00
AA-Omniscience Hallucination Rate#16 of 200.55
𝜏³-Banking: Cost per Task#16 of 200.00
Humanity's Last Exam: Output Tokens per Task#17 of 20606
Terminal-Bench v4.0: Score#17 of 200.20
AA-LCR v1.1: Score#17 of 200.81
AA-Briefcase Elo#18 of 201202
AA-Briefcase Elo#18 of 201202
SciCode: Cost per Task#18 of 200.00
AA-Briefcase Tool Calls Breakdown, Avg per Task#19 of 2031.2
AA-Briefcase Rubric Pass Rate by File Type (Normalized)#19 of 200.59
AA-Omniscience Index: Token Usage#20 of 20721866

Price vs intelligence

Gemini 3.8 Flash (high)intelligence index →input price / 1M → $4.00
Each dot is a model, joined by AI Battle from two public datasets — the intelligence index ranking and the published input pricing ranking. Every published value is shown as-is, no averaging. The dashed line is the value frontier: no model above or to the right of it offers a lower input price at its intelligence level.

How to read this profile

Each row is a separate measurement in a separate dataset — the position reflects the metric of that ranking, and a higher number is not "better" for every dataset (times and prices are costs). AI Battle deliberately does not average placements into a single score: datasets differ in coverage, so a total would hide more than it shows.

Raw data

Machine-readable profile: /data/models/gemini-3-8-flash.json.

Method

Placements, joins and this page are computed by AI Battle from public datasets — see the methodology for sources, limitations and corrections.